Segmentation of Moving Objects by Long Term Video Analysis
Lists
Only you see this
Abstract
Motion is a strong cue for unsupervised object-level grouping. In this paper, we demonstrate that motion will be exploited most effectively, if it is regarded over larger time windows. Opposed to classical two-frame optical flow, point trajectories that span hundreds of frames are less susceptible to short-term variations that hinder separating different objects. As a positive side effect, the resulting groupings are temporally consistent over a whole video shot, a property that requires tedious post-processing in the vast majority of existing approaches. We suggest working with a paradigm that starts with semi-dense motion cues first and that fills up textureless areas afterwards based on color. This paper also contributes the Freiburg-Berkeley motion segmentation (FBMS) dataset, a large, heterogeneous benchmark with 59 sequences and pixel-accurate ground truth annotation of moving objects.
BibTeX
@article{ochs2014segmentation,
author = {Peter Ochs and Jitendra Malik and Thomas Brox},
title = {{Segmentation of Moving Objects by Long Term Video Analysis}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2014},
doi = {10.1109/tpami.2013.242},
}Loading related content...